© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75184
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geograf
    -1.26
     accompagner
    -1.10
     geha
    -1.05
     versie
    -1.05
     empêcher
    -1.04
     gema
    -1.02
     kara
    -1.02
     gekocht
    -1.02
     verlang
    -1.01
     gefe
    -1.01
    POSITIVE LOGITS
     jornalista
    1.09
    indiri
    1.09
     devemos
    1.07
    urably
    1.06
     fomentar
    1.02
    に於
    1.02
     cancelamento
    1.02
     céramique
    1.01
    ÁND
    1.01
     shipped
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.